Follow RFC793 section "SEGMENT ARRIVES".
There are 4 major cases:
1) If the state is CLOSED
2) If the state is LISTEN
3) If the state is SYN-SENT
4) If the state is other state
Note:
- This change is significant (more than 10 pages in RFC793 describing
this segment arrival handling).
- More test is needed. Good news is, so far, tcp_server(ping/txtx/rxrx)
tests and httpd work fine.
Build a 128-entry redirection table to select which cpu services which
packet, when we have more cores than queues (and thus need to dispatch
internally).
Add a --hw-queue-weight to control the relative weight of the hardware queue.
With a weight of 0, the core that services the hardware queue will not
process any packets; with a weight of 1 (default) it will process an equal
share of packets, compared to proxy queues.
Unlike tcp::tcb::send() and tcp::connection::send() which send tcp
packets associated with tcb, tcp::send() only send packets associated
without tcb. We have a bunch of send() functions, rename it to make the
code more readable.
Tested with tcp_server + client.go using iptables dropping <SYN,ACK> or
<FIN,ACK> on client side.
I verified that the SYN or FIN packet is retransmitted and the
connection is closed after N (currently 5) retries.
rss_bits should be equal to the number of bits HW used in its RSS calculation.
Use dev_info.max_rx_queues if dev_info.reta_size is not available.
Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
With SO_REUSEPORT, we can bind() & accept() on each thread, kernel will dispatch incomming connections.
Signed-off-by: Takuya ASADA <syuu@cloudius-systems.com>
- Adjust the asserts.
- Add an assert in the place where we should not get if RSS info is not provided.
Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: Avi Kivity <avi@cloudius-systems.com>
Some packets generated by tcp do not belong to any connection. Currently
such packets are pushed to ipv4 directly. This patch adds a packet queue
for ipv4 to poll them from and limits amount of memory those packets can
consume.
This patch change tcp to register a poller so that l3 can poll tcp for
a packet instead of pushing packets from tcp to ipv4. This pushes
networking tx path inversion a little bit closer to an application.
Currently udp sender my send whenever it has data and if it does
this faster than packets can be transmitted we will run out of memory.
This patch limits how much outstanding data each native udp channel may
have.
L4 will provide the callback to be called by L3 after the packet is
handled to lower layers for transmission. L4 will know that it can queue
more data from user at this point. The patch also change send function
that can no longer block to return void instead of future<>.
